© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 6718
    Prev
    Next
    INDEX
    Explanations

    concepts related to guilt and innocence in legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_8/width_16k/average_l0_99
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     houſe
    -0.52
     vœ
    -0.51
    ifikationer
    -0.47
     retos
    -0.45
     meille
    -0.44
     Viana
    -0.44
     vôtre
    -0.42
     mijne
    -0.41
     circons
    -0.41
    További
    -0.41
    POSITIVE LOGITS
     blame
    1.32
     guilty
    1.28
    guilty
    1.25
     Blame
    1.23
    Blame
    1.19
     guilt
    1.17
     Guilt
    1.13
     blaming
    1.11
     Guilty
    1.11
     blames
    1.07
    Activations Density 0.266%

    No Known Activations